SDDGR: Stable Diffusion-Based Deep Generative Replay for Class Incremental Object Detection

In the field of class incremental leaming (CIL), generative replay has become increasingly prominent as a method to mitigate the catastrophic forgetting, alongside the continuous improvements in generative models. However, its application in class incremental object detection (CIOD) has been signifi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) S. 28772 - 28781
Hauptverfasser: Kim, Junsu, Cho, Hoseong, Kim, Jihyeon, Tiruneh, Yihalem Yimolal, Baek, Seungryul
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 16.06.2024
Schlagworte:
Class Incremental Object detection
Complexity theory
Computational efficiency
Computer vision
Continual learning
deep generative
Incremental learning
Object detection
Pattern recognition
Regulation
replay
Stable diffusion
Text to image
ISSN:1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In the field of class incremental leaming (CIL), generative replay has become increasingly prominent as a method to mitigate the catastrophic forgetting, alongside the continuous improvements in generative models. However, its application in class incremental object detection (CIOD) has been significantly limited, primarily due to the complexities of scenes involving multiple labels. In this paper, we propose a novel approach called stable diffusion deep generative replay (SDDGR) for CIOD. Our method utilizes a diffusion-based generative model with pre-trained text-to-image diffusion networks to generate realistic and diverse synthetic images. SDDGR incorporates an iterative refinement strategy to produce high-quality images encompassing old classes. Additionally, we adopt an L2 knowledge distillation technique to improve the retention of prior knowledge in synthetic images. Furthermore, our approach includes pseudo-labeling for old objects within new task images, preventing misclassification as background elements. Extensive experiments on the COCO 2017 dataset demonstrate that SD-DGR significantly outperforms existing algorithms, achieving a new state-of-the-art in various CIOD scenarios.
ISSN:1063-6919
DOI:10.1109/CVPR52733.2024.02718